Hansa


Back to catalogue >>

Reference: Acharya V. and Nagarajaram H.A. Hansa: An automated method for discriminating disease and neutral human nsSNPs. Human Mutation (2012) 2:332-337.
Hosted: Developed and maintained by the Laboratory of Computational Biology, Centre for DNA fingerprinting and diagnostics, Nampally, Hyderabad. (http://hansa.cdfd.org.in:8080/)

Summary:
Hansa uses a support vector machine (SVM) trained on a combination of position-specific, structural and amino acid features.

Methodology:
Hansa is trained on the HumVar mutation data also implemented in the PhD-SNP and Parepro algorithms. This dataset comprises 13032 disease-related substitutions from 1111 genes and 8946 neutral substitutions from 3484 genes.
Hansa combines 10 different properties of these substitutions to partition disease and neutral mutations.
• 6 features related to the specific position of the mutation and probabilities of the amino acids.
• 2 features of protein structural environment.
• 2 features based on likelihood of the amino acid substitutions.

Alignments for the query protein are generated using PSI-BLAST.

Input:
The user can provide a database ID, GenBank, RefSeq, SWISSPROT or PDB identifier for the query protein. Alternatively the protein sequence can be pasted or uploaded. The mutation(s) can then be provided.

Output:
Mutations are predicted as ‘disease’ or ‘neutral’ and a breakdown of each of the parameter scores are provided.